© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5977
    Prev
    Next
    INDEX
    Explanations

    assertions that there is nothing in the evidence or record

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewGroup
    -0.48
    noe
    -0.40
     Their
    -0.40
     their
    -0.39
    ัญ
    -0.39
    fe
    -0.38
    ronic
    -0.38
     mas
    -0.38
    elk
    -0.37
    Their
    -0.37
    POSITIVE LOGITS
     Monfieur
    1.09
     Efq
    1.05
     purpoſe
    1.03
     himſelf
    1.02
     becauſe
    1.02
     Eſ
    1.02
     itſelf
    1.02
     Jefus
    1.01
     myſelf
    1.01
     Diſ
    1.00
    Activations Density 0.539%

    No Known Activations